[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Home Page:https://llava.hliu.cc
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
HJLQZ opened this issue 22 days ago · comments
im trying to get visual&textual embeddings ,or the final mixed embeddings from llava,but cant find any tutorials about this. Does anyone know how to get embeddings?